for col_schema in schema:
col_name = col_schema["name"]
col_type = col_schema["type"].lower()
transform = features[col_name]["transform"]
// Map the target transfrom into one_hot or identity.
if transform == constant.TARGET_TRANSFORM:
if col_type == constant.STRING_SCHEMA:
transform = constant.ONE_HOT_TRANSFORM
elif col_type in constant.NUMERIC_SCHEMA:
transform = constant.IDENTITY_TRANSFORM
else:
raise ValueError("Unknown schema type")
if transform in (constant.TEXT_TRANSFORMS + constant.CATEGORICAL_TRANSFORMS):
if transform in constant.TEXT_TRANSFORMS:
// Split strings on space, then extract labels and how many rows each
After Change
inverted_features_target = copy.deepcopy(inverted_features)
for name, transform_set in six.iteritems(inverted_features_target):
if transform_set == set([constant.TARGET_TRANSFORM]):
target_schema = next(col["type"].lower() for col in schema if col["name"] == name)
if target_schema in constant.NUMERIC_SCHEMA:
inverted_features_target[name] = {constant.IDENTITY_TRANSFORM}
else:
inverted_features_target[name] = {constant.ONE_HOT_TRANSFORM}
